Sensor fusion for low power occupancy sensing

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current occupancy sensing systems in buildings face challenges in accurately detecting stationary occupants, distinguishing between humans and pets, and efficiently managing energy consumption, due to limitations in video-based systems, ultrasonic sensors, and passive infrared sensors.

Innovation Solution

A system combining color sensors to establish a background color map and time-of-flight sensors to determine height and velocity data, allowing for accurate occupant detection and discrimination between humans and pets, while minimizing energy consumption by using low-power sensors.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If video-based systems are used for occupancy detection, then occupancy detection capability is improved, but computational complexity and data processing overhead increase

Engineering Contradiction:
Improveoccupancy detection capabilityVSAvoidcomputational complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent extracts and removes the computationally intensive video processing component from the occupancy detection system. Instead of using full video feeds, the system uses only depth data from time-of-flight sensors and color data from color sensors, eliminating the need for complex image recognition algorithms while maintaining occupancy detection capability.

Inventive Principle:
Principle #2Taking out (Extraction)

Solution Approach 2:

The patent replaces the optical-mechanical video-based detection system with a sensor fusion approach using time-of-flight depth sensing and color sensing. This substitution eliminates the need for complex video processing hardware and software, reducing computational complexity while maintaining detection accuracy.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

2Measurement precision

If video-based systems are used for occupancy detection, then occupancy detection capability is improved, but data processing overhead increases

Engineering Contradiction:
Improveoccupancy detection capabilityVSAvoiddata processing overhead
Core Design Contradiction:
Measurement precisionVSUse of energy by moving object

Solution Approach 1:

The patent extracts only the essential data elements (depth and color) needed for occupancy detection, discarding the bulk of video data that would require processing. This extraction approach dramatically reduces data processing overhead and energy consumption while maintaining detection capability.

Inventive Principle:
Principle #2Taking out (Extraction)

3Measurement precision

If ultrasonic sensors are used for occupancy detection, then motion detection capability is improved, but false positives increase

Engineering Contradiction:
Improvemotion detection capabilityVSAvoidfalse positive rate
Core Design Contradiction:
Measurement precisionVSReliability

Solution Approach 1:

The patent merges ultrasonic motion detection with color sensor data and time-of-flight depth sensing. By combining multiple sensor modalities, the system can distinguish between actual occupants and false positive sources like moving air streams, significantly reducing false positive rates while maintaining motion detection capability.

Inventive Principle:
Principle #5Merging (Combining)

4Use of energy by moving object

If PIR sensors are used for occupancy detection, then power consumption is reduced, but stationary occupant detection fails

Engineering Contradiction:
Improvepower consumptionVSAvoidstationary occupant detection
Core Design Contradiction:
Use of energy by moving objectVSMeasurement precision

Solution Approach 1:

The patent merges PIR sensor low-power operation with time-of-flight depth sensing and color sensing. The PIR sensor provides motion-triggered wake-up signals, while the time-of-flight and color sensors continuously monitor for stationary occupants, achieving both low power consumption and accurate stationary occupant detection.

Inventive Principle:
Principle #5Merging (Combining)

5Use of energy by moving object

If color sensors are used for occupancy detection, then power consumption is reduced, but discrimination between humans and pets is lost

Engineering Contradiction:
Improvepower consumptionVSAvoidoccupancy discrimination
Core Design Contradiction:
Use of energy by moving objectVSMeasurement precision

Solution Approach 1:

The patent merges color sensor data with time-of-flight depth data to enable discrimination between humans and pets. The combination of color information and height/depth measurements allows the system to distinguish human occupants from pets while maintaining the low power consumption characteristics of color sensors.

Inventive Principle:
Principle #5Merging (Combining)

6Reliability

If PIR and ultrasonic sensors are combined for occupancy detection, then false positive events are reduced, but stationary occupant detection remains impossible

Engineering Contradiction:
Improvefalse positive reductionVSAvoidstationary occupant detection
Core Design Contradiction:
ReliabilityVSMeasurement precision

Solution Approach 1:

The patent merges PIR and ultrasonic sensor benefits (false positive reduction through multi-sensor validation) with time-of-flight depth sensing capability (stationary occupant detection). The time-of-flight sensor provides continuous monitoring for stationary occupants while the PIR and ultrasonic sensors validate motion-based detections, achieving both goals simultaneously.

Inventive Principle:
Principle #5Merging (Combining)

Applied Scientific Principles

This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.

Function Achieved in This Case

The system effectively detects and tracks occupants, reducing false positives and negatives, and optimizing energy use in smart building systems by accurately controlling lighting and HVAC systems.

Implementation Method 1

at least one second sensor configured to determine height data of the at least one occupant

Methodology Applied
Scientific EffectTime of flight: Time of Flight

Implementation Method 2

color sensors can detect the time dependent changes in reflected light SPDs caused by occupant presence

Methodology Applied
Scientific EffectLight reflection: Reflection

Data Source

PatentUS20240318856A1Sensor fusion for low power occupancy sensing
Publication Date: 2024.09.26 RENESSELAER POLYTECHNIC INST
  • US20240318856A1 patent drawing
  • US20240318856A1 patent drawing
  • US20240318856A1 patent drawing

AI summary

A system for detecting occupants in a room is provided. The system includes at least one first sensor configured to establish a background color map of the room in an unoccupied state and to detect color shift data resulting from at least one occupant entering the room, at least one second sensor configured to determine height data of the at least one occupant, and a controller configured to receive the color shift data and the height data and to generate equipment-control signals to operate at least one occupant-centric system.